季节ARIMA模型在我国肺结核发病率预测中的应用

Application of Seasonal ARIMA Model in Forecasting Incidence of Tuberculosis

目的探讨应用季节ARIMA模型对我国肺结核发病率进行预测的可行性.方法对我国2005年1月-2010年12月肺结核逐月发病率建立季节ARIMA模型,并对预测效果进行评价.结果 ARIMA(3,1,0)×(0,1,1)12模型很好地拟合了既往数据,对2011年1月-9月发病率的预测值符合实际发病率变动趋势.结论季节ARIMA模型能很好地模拟我国肺结核发病率的变动趋势,将其应用于肺结核发病率预测是可行的.

[Objective]To explore the feasibility of Seasonal Autoregressive Integrated Moving Average（SARIMA）model to predict the incidence of tuberculosis in China. [Methods] SARIMA model was established based on the incidence of tuberculosis in China during 2005.01- 2010.12 and the prediction effect of SARIMA model was also evaluated. [Results]Model of ARI- MA（3,1,0）× （0,1,1）lz exactly fitted the incidence in the previous months. The fit values of inci- dence during 2011.01--2011.09 were consistent with the actual data of incidence. [Conclusion] SARIMA model can be used to exactly to fit the changes of the incidence of tuberculosis in China and to predict the incidence in future.